Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Inspect your agent's session with /𝚝𝚛𝚊𝚌𝚎𝚜. Gain full visibility into prompts, tool calls, errors, cost, and subagent work directly from the terminal.

eve's profile picture

eve

12,040 subscribers

15,869 görüntüleme • 1 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Meet Sessions. View the full, inspectable timeline of an AI-assisted coding session, then filter down to prompts, responses, intermediate steps, checkpoints, and tool calls. Understand what happened, not just what changed. 😉
0:18

Meet Sessions. View the full, inspectable timeline of an AI-assisted coding session, then filter down to prompts, responses, intermediate steps, checkpoints, and tool calls. Understand what happened, not just what changed. 😉

Entire

27,067 görüntüleme • 4 ay önce

You can now resume your terminal sessions in the Claude Code desktop app. Type /resume to pick any session you started from the CLI. The session continues in the app with the full conversation and context intact.
0:10

You can now resume your terminal sessions in the Claude Code desktop app. Type /resume to pick any session you started from the CLI. The session continues in the app with the full conversation and context intact.

ClaudeDevs

648,455 görüntüleme • 18 gün önce

Zap Out directly from your DLMM position. ⚡️ Close any DLMM position and swap into SOL or USDC in one flow. Now available on the Dynamic Terminal.
0:18

Zap Out directly from your DLMM position. ⚡️ Close any DLMM position and swap into SOL or USDC in one flow. Now available on the Dynamic Terminal.

Meteora

19,344 görüntüleme • 4 gün önce

I built a TUI design tool for my work at OpenCode and I’ve been using it for the last 2 weeks → Design directly on the terminal grid → ASCII borders that join automatically → Flexbox, multiplayer, sections etc
0:12

I built a TUI design tool for my work at OpenCode and I’ve been using it for the last 2 weeks → Design directly on the terminal grid → ASCII borders that join automatically → Flexbox, multiplayer, sections etc

Aarav Sareen

108,106 görüntüleme • 21 gün önce

You can now view Knowledge Base retrieval chunks directly in the Test LLM feature🌐 Get full visibility into how your Knowledge Base is being used. Instantly verify whether queries retrieve the right information — and fine-tune as needed.
0:11

You can now view Knowledge Base retrieval chunks directly in the Test LLM feature🌐 Get full visibility into how your Knowledge Base is being used. Instantly verify whether queries retrieve the right information — and fine-tune as needed.

Sayly AI

60,480 görüntüleme • 7 ay önce

Explore your Hugging Face repos in a whole new way 🔥 Visualize storage, discover outliers, and navigate your repos directly from the terminal. `hf repos ls --explore`
0:12

Explore your Hugging Face repos in a whole new way 🔥 Visualize storage, discover outliers, and navigate your repos directly from the terminal. `hf repos ls --explore`

Julien Chaumond

27,706 görüntüleme • 3 ay önce

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.
0:18

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

BuBBliK

200,456 görüntüleme • 3 ay önce

Once you get familiar with Termius, it really makes vibe coding on the go much easier. > Hold space + swipe for arrow keys > Create new session `tmux new -s ` > Attach anytime `tmux attach` > Switch b/w Claude Code or Codex easily > Work on different projects All happening right on your macOS terminal from your phone. > No VPS > No GitHub PRs > No Cloud environments Literally directly working on your mac from your phone!
0:19

Once you get familiar with Termius, it really makes vibe coding on the go much easier. > Hold space + swipe for arrow keys > Create new session `tmux new -s ` > Attach anytime `tmux attach` > Switch b/w Claude Code or Codex easily > Work on different projects All happening right on your macOS terminal from your phone. > No VPS > No GitHub PRs > No Cloud environments Literally directly working on your mac from your phone!

Chong-U

17,128 görüntüleme • 7 ay önce

Just like a physical notebook, your digital notebooks should go wherever you work. 📓 You can already access and create notebooks directly within the Google Gemini, with full cross-app syncing between the Gemini app and the standalone Gemini Notebook experience. Soon, we’ll also bring notebooks directly into AI Mode in Search.🔍✨
0:15

Just like a physical notebook, your digital notebooks should go wherever you work. 📓 You can already access and create notebooks directly within the Google Gemini, with full cross-app syncing between the Gemini app and the standalone Gemini Notebook experience. Soon, we’ll also bring notebooks directly into AI Mode in Search.🔍✨

Google

38,989 görüntüleme • 2 ay önce

It's never been easier to do everyday work with Codex. Choose your role, connect the apps you use every day, and try suggested prompts. Codex helps with everything from research and planning to docs, slides, spreadsheets, and more.
0:15

It's never been easier to do everyday work with Codex. Choose your role, connect the apps you use every day, and try suggested prompts. Codex helps with everything from research and planning to docs, slides, spreadsheets, and more.

OpenAI

1,531,408 görüntüleme • 4 ay önce

Vulcan is live. The official command-line tool for Phoenix — built for traders and AI agents. Trade, stream live markets, and run strategies from your terminal. Or let an agent drive.
0:16

Vulcan is live. The official command-line tool for Phoenix — built for traders and AI agents. Trade, stream live markets, and run strategies from your terminal. Or let an agent drive.

Phoenix

175,279 görüntüleme • 3 ay önce

Prediction markets are coming to LAB Terminal LAB is integrating with DFlow and Kalshi to bring real-world probabilities onchain and into execution - Place prediction orders directly from LAB - Real-world outcomes become tradeable signals - One terminal for spot, perps, and now probabilities Trade narratives before they become consensus
0:19

Prediction markets are coming to LAB Terminal LAB is integrating with DFlow and Kalshi to bring real-world probabilities onchain and into execution - Place prediction orders directly from LAB - Real-world outcomes become tradeable signals - One terminal for spot, perps, and now probabilities Trade narratives before they become consensus

LAB

83,753 görüntüleme • 6 ay önce

Introducing cmux Vault: cmux now has a right sidebar with a vault pane where you can see every single Codex, Claude Code, OpenCode, and Pi session You can search through all sessions with full-text search, and drag them directly into your workspace Out in v0.64+
0:15

Introducing cmux Vault: cmux now has a right sidebar with a vault pane where you can see every single Codex, Claude Code, OpenCode, and Pi session You can search through all sessions with full-text search, and drag them directly into your workspace Out in v0.64+

Lawrence Chen

32,394 görüntüleme • 4 ay önce

Windsurf now has Browser Previews! Not only did we bring preview functionality directly into the editor, but now you can also select individual components (and errors!) as @-mentions to send to Cascade in your next prompt.
0:16

Windsurf now has Browser Previews! Not only did we bring preview functionality directly into the editor, but now you can also select individual components (and errors!) as @-mentions to send to Cascade in your next prompt.

Devin Desktop

59,548 görüntüleme • 1 yıl önce

this is pure f*cking treasure these 10 agent skills have 8.01M combined downloads and form a complete working stack discovery. pressure-testing. design. browser work. prototyping. debugging. vision. orchestration. tool building 01 find-skills ▸ 02 grill-me ▸ 03 frontend-design ▸ 04 agent-browser ▸ 05 prototype ▸ 06 diagnosing-bugs ▸ 07 skill-creator ▸ 08 image-to-code ▸ 09 subagent-driven-development ▸ 10 mcp-builder ▸ the stack covers the full loop: find the capability ⮕ shape the idea ⮕ build it ⮕ inspect it ⮕ verify it and package the workflow for the next run save this, then select your gpt-6 astra use case ⭣
0:18

this is pure f*cking treasure these 10 agent skills have 8.01M combined downloads and form a complete working stack discovery. pressure-testing. design. browser work. prototyping. debugging. vision. orchestration. tool building 01 find-skills ▸ 02 grill-me ▸ 03 frontend-design ▸ 04 agent-browser ▸ 05 prototype ▸ 06 diagnosing-bugs ▸ 07 skill-creator ▸ 08 image-to-code ▸ 09 subagent-driven-development ▸ 10 mcp-builder ▸ the stack covers the full loop: find the capability ⮕ shape the idea ⮕ build it ⮕ inspect it ⮕ verify it and package the workflow for the next run save this, then select your gpt-6 astra use case ⭣

beamnxw ./

49,163 görüntüleme • 2 gün önce

Succesfully integrated seedance 2.0 api into our internal pipeline 🙂 custom prompts based on each article with the ability to edit, reroll, and work in tandem with a larger team
0:10

Succesfully integrated seedance 2.0 api into our internal pipeline 🙂 custom prompts based on each article with the ability to edit, reroll, and work in tandem with a larger team

PsyopAnime

29,793 görüntüleme • 2 ay önce

Warp now has built-in support for the Grok Build CLI. - Use Warp's rich input for agent prompts, with support for longer pasted prompts and multi-cursor - Use /remote-control to share your agent session to another device - Access the file explorer and code review panels
0:13

Warp now has built-in support for the Grok Build CLI. - Use Warp's rich input for agent prompts, with support for longer pasted prompts and multi-cursor - Use /remote-control to share your agent session to another device - Access the file explorer and code review panels

Warp

506,400 görüntüleme • 4 gün önce